Package SloppyCell :: Module Optimization
[hide private]

Module Optimization

source code

Classes [hide private]
  KeyedList
Functions [hide private]
 
fmin_powell_log_params(m, params, *args, **kwargs) source code
 
fmin_log_params(m, params, *args, **kwargs) source code
 
fmin(m, params, *args, **kwargs) source code
 
fmin_xform(m, params, xforms, invforms, *args, **kwargs)
Nelder-Mead the cost over an arbitrary transform on the parameters.
source code
 
fmin_lm_log_params(m, params, *args, **kwargs)
Minimize the cost of a model using Levenberg-Marquadt in terms of log parameters.
source code
 
leastsq_log_params(m, params, *args, **kwargs) source code
Variables [hide private]
  logger = logging.getLogger('Optimization')

Imports: copy, sys, logging, scipy, KeyedList_mod, Utility, lmopt


Function Details [hide private]

fmin_xform(m, params, xforms, invforms, *args, **kwargs)

source code 

Nelder-Mead the cost over an arbitrary transform on the parameters.

m         Model to minimize the cost for
params    initial parameter estimate
xforms    sequence of transforms (of length, len(params)) to apply to the 
          parameters before optimizing
invforms  sequences of inverse transforms to get back to straight parameters
*args     passed on to scipy.optimize.fmin
**kwargs  passed on to scipy.optimize.fmin
          For information on these, consult help(scipy.optimize.fmin)

fmin_lm_log_params(m, params, *args, **kwargs)

source code 

Minimize the cost of a model using Levenberg-Marquadt in terms of log 
parameters.

The *args and **kwargs represent additional parmeters that will be passed to
the optimization algorithm. For your convenience, the docstring of that
function is appended below: